© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 17820
    Prev
    Next
    INDEX
    Explanations

    terms related to economic modeling and assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oste
    -0.07
    Ø´ÙĨ
    -0.07
    orc
    -0.06
    iga
    -0.06
     dipl
    -0.06
    çĢ
    -0.06
    baugh
    -0.06
    å®Į
    -0.06
    lauf
    -0.06
    amet
    -0.06
    POSITIVE LOGITS
     assumptions
    0.13
     assumption
    0.11
     assumed
    0.10
     premises
    0.10
     Ass
    0.10
     chosen
    0.09
    ASS
    0.08
    åģĩ
    0.08
    chosen
    0.08
     ASS
    0.08
    Activations Density 0.147%

    No Known Activations